Triple
T22152610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johnny Jones |
E547449
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object |
Carol Fisher
Carol Fisher is an individual known primarily for her association with Johnny Jones.
|
E1528700
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Carol Fisher | Statement: [Johnny Jones, associatedWith, Carol Fisher]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carol Fisher Context triple: [Johnny Jones, associatedWith, Carol Fisher]
-
A.
Diane Coulston
Diane Coulston is a teenage schoolgirl in the film "T2 Trainspotting," known for her past relationship with protagonist Mark Renton and her sharp, grounded perspective on the aging former heroin users.
-
B.
Christine Forrest
Christine Forrest is an American actress and producer best known for her long-time collaboration and marriage with horror filmmaker George A. Romero.
-
C.
Kat C. Howard
Kat C. Howard is the wife of American actor Clint Howard.
-
D.
Karen Disher
Karen Disher is an American storyboard artist, director, and voice actress known for her work on animated films and television series, including the Ice Age franchise.
-
E.
Lori Marshall
Lori Marshall is an American television writer and author, known for her work on sitcoms and for collaborating on books about and with her father, filmmaker Garry Marshall.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Carol Fisher Triple: [Johnny Jones, associatedWith, Carol Fisher]
Generated description
Carol Fisher is an individual known primarily for her association with Johnny Jones.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Carol Fisher Target entity description: Carol Fisher is an individual known primarily for her association with Johnny Jones.
-
A.
Diane Coulston
Diane Coulston is a teenage schoolgirl in the film "T2 Trainspotting," known for her past relationship with protagonist Mark Renton and her sharp, grounded perspective on the aging former heroin users.
-
B.
Christine Forrest
Christine Forrest is an American actress and producer best known for her long-time collaboration and marriage with horror filmmaker George A. Romero.
-
C.
Kat C. Howard
Kat C. Howard is the wife of American actor Clint Howard.
-
D.
Karen Disher
Karen Disher is an American storyboard artist, director, and voice actress known for her work on animated films and television series, including the Ice Age franchise.
-
E.
Lori Marshall
Lori Marshall is an American television writer and author, known for her work on sitcoms and for collaborating on books about and with her father, filmmaker Garry Marshall.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e11e3b52088190ad5df386d01eb2fb |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129f5a740819093628386732b91a6 |
completed | April 28, 2026, 9:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0abc8f62b481909039b1e4f2dea745 |
completed | May 18, 2026, 7:15 a.m. |
| NEDg | Description generation | batch_6a0abe6f29708190b5a770042e06f34b |
completed | May 18, 2026, 7:23 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0abf2d6e988190b1707717e5f20347 |
completed | May 18, 2026, 7:26 a.m. |
Created at: April 16, 2026, 8:33 p.m.